English
Related papers

Related papers: How Does Learning Rate Decay Help Modern Neural Ne…

200 papers

Neoteric works have shown that modern deep learning models can exhibit a sparse double descent phenomenon. Indeed, as the sparsity of the model increases, the test performance first worsens since the model is overfitting the training data;…

Machine Learning · Computer Science 2024-02-09 Victor Quétu , Enzo Tartaglione

While training error of most deep neural networks degrades as the depth of the network increases, residual networks appear to be an exception. We show that the main reason for this is the Lyapunov stability of the gradient descent…

Machine Learning · Computer Science 2018-03-23 Kamil Nar , Shankar Sastry

Deep neural network (DNN) usually learns the target function from low to high frequency, which is called frequency principle or spectral bias. This frequency principle sheds light on a high-frequency curse of DNNs -- difficult to learn…

Machine Learning · Computer Science 2022-08-23 Tao Luo , Zheng Ma , Zhiwei Wang , Zhi-Qin John Xu , Yaoyu Zhang

Deep neural networks are known to exhibit a `double descent' behavior as the number of parameters increases. Recently, it has also been shown that an `epochwise double descent' effect exists in which the generalization error initially…

Machine Learning · Computer Science 2021-08-30 Cory Stephenson , Tyler Lee

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well…

Machine Learning · Computer Science 2023-02-17 Amirkeivan Mohtashami , Martin Jaggi , Sebastian Stich

Pre-trained deep neural networks (DNNs) are being widely deployed by industry for making business decisions and to serve users; however, a major problem is model decay, where the DNN's predictions become more erroneous over time, resulting…

Computer Vision and Pattern Recognition · Computer Science 2024-09-18 Md Yousuf Harun , Christopher Kanan

Training a neural network with the gradient descent algorithm gives rise to a discrete-time nonlinear dynamical system. Consequently, behaviors that are typically observed in these systems emerge during training, such as convergence to an…

Machine Learning · Computer Science 2018-10-10 Kamil Nar , S. Shankar Sastry

Weight decay is a widely used technique for training Deep Neural Networks(DNN). It greatly affects generalization performance but the underlying mechanisms are not fully understood. Recent works show that for layers followed by…

Machine Learning · Computer Science 2021-03-30 Yucong Zhou , Yunxiao Sun , Zhao Zhong

The backpropagation algorithm remains the dominant and most successful method for training deep neural networks (DNNs). At the same time, training DNNs at scale comes at a significant computational cost and therefore a high carbon…

Machine Learning · Computer Science 2025-11-12 Sander Dalm , Joshua Offergeld , Nasir Ahmad , Marcel van Gerven

Batch Normalization is a commonly used trick to improve the training of deep neural networks. These neural networks use L2 regularization, also called weight decay, ostensibly to prevent overfitting. However, we show that L2 regularization…

Machine Learning · Computer Science 2017-06-19 Twan van Laarhoven

Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many layers can be highly desirable at test time, training very…

Machine Learning · Computer Science 2016-08-01 Gao Huang , Yu Sun , Zhuang Liu , Daniel Sedra , Kilian Weinberger

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

Machine Learning · Statistics 2018-06-15 Atsushi Nitanda , Taiji Suzuki

Large-scale deep neural networks (DNN) have been successfully used in a number of tasks from image recognition to natural language processing. They are trained using large training sets on large models, making them computationally and…

Machine Learning · Computer Science 2017-03-28 Sek Chai , Aswin Raghavan , David Zhang , Mohamed Amer , Tim Shields

Multilayer networks have seen a resurgence under the umbrella of deep learning. Current deep learning algorithms train the layers of the network sequentially, improving algorithmic performance as well as providing some regularization. We…

Machine Learning · Computer Science 2016-02-22 Ke Wu , Malik Magdon-Ismail

Weight decay (WD) is a traditional regularization technique in deep learning, but despite its ubiquity, its behavior is still an area of active research. Golatkar et al. have recently shown that WD only matters at the start of the training…

Machine Learning · Computer Science 2020-12-29 Johan Bjorck , Kilian Weinberger , Carla Gomes

Traditional analyses of gradient descent optimization show that, when the largest eigenvalue of the loss Hessian - often referred to as the sharpness - is below a critical learning-rate threshold, then training is 'stable' and training loss…

Machine Learning · Computer Science 2024-12-24 Lawrence Wang , Stephen J. Roberts

The choice of initial learning rate can have a profound effect on the performance of deep networks. We present a class of neural networks with solvable training dynamics, and confirm their predictions empirically in practical deep learning…

Machine Learning · Statistics 2020-03-05 Aitor Lewkowycz , Yasaman Bahri , Ethan Dyer , Jascha Sohl-Dickstein , Guy Gur-Ari

A vast literature on convergence guarantees for gradient descent and derived methods exists at the moment. However, a simple practical situation remains unexplored: when a fixed step size is used, can we expect gradient descent to converge…

Machine Learning · Computer Science 2024-12-10 Alexandru Crăciun , Debarghya Ghoshdastidar

Learning rate warm-up - increasing the learning rate at the beginning of training - has become a ubiquitous heuristic in modern deep learning, yet its theoretical foundations remain poorly understood. In this work, we provide a principled…

Machine Learning · Computer Science 2025-10-06 Foivos Alimisis , Rustem Islamov , Aurelien Lucchi

Learning deeper convolutional neural networks becomes a tendency in recent years. However, many empirical evidences suggest that performance improvement cannot be gained by simply stacking more layers. In this paper, we consider the issue…

Computer Vision and Pattern Recognition · Computer Science 2016-04-05 Li Shen , Zhouchen Lin , Qingming Huang
‹ Prev 1 4 5 6 7 8 10 Next ›